检索结果-内蒙古大学图书馆

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Jianxin Li Shuai Zhang Hui Xiong Haoyi Zhou Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China Hong Kong University of Science and Technology (Guangzhou) Guangzhou HKUST Fok Ying Tung Research Institute Guangzhou China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China

ISBN: (纸本)9781713871088

The analysis of spatio-temporal sequences plays an important role in many real-world applications, demanding a high model capacity to capture the interdependence among spatial and temporal dimensions. Previous studies provided separated network design in three categories: spatial first, temporal first, and spatio-temporal synchronous. However, the manually-designed heterogeneous models can hardly meet the spatio-temporal dependency capturing priority for various tasks. To address this, we proposed a universal modeling framework with three distinctive characteristics: (i) Attention-based network backbone, including S2T Layer (spatial first), T2S Layer (temporal first), and STS Layer (spatio-temporal synchronous). (ii) The universal modeling framework, named UniST, with a unified architecture that enables flexible modeling priorities with the proposed three different modules. (iii) An automatic search strategy, named AutoST, automatically searches the optimal spatio-temporal modeling priority by network architecture search. Extensive experiments on five real-world datasets demonstrate that UniST with any single type of our three proposed modules can achieve state-of-the-art performance. Furthermore, AutoST can achieve overwhelming performance with UniST.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hybrid Resource Orchestration and Scheduling for Cyber-Physical-Human Systems 22

Hybrid Resource Orchestration and Scheduling for Cyber-Physi...

引用

22nd IEEE International Conference on High Performance computing and Communications, 18th IEEE International Conference on Smart City and 6th IEEE International Conference on data Science and Systems, HPCC-SmartCity-DSS 2020

作者： Zhu, Jianyong Wang, Xu Wo, Tianyu Hu, Chunming Beihang University Beijing Advanced Innovation Center for Big Data and Brain Computing China

ISBN: (纸本)9781728176499

Recently Cyber-Physical-Human Systems (CPHS) have been attracted much attention. Unlike existing computing paradigms such as Cloud computing and Edge computing, CPHS usually comprise many types of hybrid resources such as software and hardware in the cloud layer, network devices and edge servers in the network layer, as well as the physical devices and human participation. Such hybrid resource makes it challenging to efficient resource scheduling for CPHS. Previous studies on CPHS often focus on improving scheduling efficiency for specific application scenarios and thus are limited for other CPHS. In this work, we present a unified hybrid resource scheduling framework for CPHS, including a hybrid resource model for multiple types of resource providers and participants in CPHS, a hybrid resource orchestration tool that can describe our hybrid resource model as the resource requirements, and a scheduling mechanism to satisfy the resource requirements especially by considering the resource constraints and crosslayer scheduling in CPHS. We perform the case study of typical CPHS scenarios and show that our hybrid resource model and scheduling framework is effective, and provide a new view for improving the resource provision efficiency in CPHS. © 2020 IEEE.

关键词： Network layers

来源：评论

学校读者我要写书评

暂无评论

DOANet: Point Cloud Registration with Deep Overlap Attention

DOANet: Point Cloud Registration with Deep Overlap Attention

引用

2021 China Automation Congress, CAC 2021

作者： Guan, Haining Gao, Qing Zhang, Baochang School of Automation Science and Electrical Engineering Beihang University Beijing100191 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China

ISBN: (纸本)9781665426473

Pairwise point cloud registration is a fundamental task in 3D computer vision and various approaches have been proposed to handle this problem in recent years. Despite the fast evolution of registration algorithms, little attention has been drawn to align point cloud pairs with a low-overlap ratio (≤30%). In this paper, we propose a new neural network architecture named the DOANet, an end-to-end trainable fully convolutional neural network, to deal with the problem of registration with low overlap. In particular, we leverage sparse convolutions to extract robust and discriminative dense features, and further utilize attention mechanisms to explicitly predict the overlap region for point cloud fragments. The receptive field of our local point patches is constrained within the overlap region generated on the fly, which prevents the local point features from being contaminated by geometric information outside the overlap region. Experiments indicate the effectiveness and advantages of our method on both 3DLoMatch (all pairs under 30% overlap-ratio) and 3DMatch and illustrate obvious improvement over the existing results. © 2021 IEEE

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

DG-CNN:Introducing Margin Information into Convolutional Neural Networks for Breast Cancer Diagnosis in Ultrasound Images

引用

Journal of Computer Science & Technology 2022年第2期37卷 277-294页

作者： Xiao-Zheng Xie Jian-Wei Niu Senior Member Xue-Feng Liu Qing-Feng Li Yong Wang Jie Han Shaojie Tang State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang UniversityBeijing 100191China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang UniversityHangzhou 310051China Department of Diagnostic Ultrasound National Cancer CenterChinese Academy of Medical SciencesPeking Union Medical CollegeBeijing 100021China Naveen Jindal School of Management The University of Texas at DallasRichardsonTX 75080-3021U.S.A.

Although using convolutional neural networks(CNNs)for computer-aided diagnosis(CAD)has made tremendous progress in the last few years,the small medical datasets remain to be the major bottleneck in this *** address this problem,researchers start looking for information out of the medical *** efforts mainly leverage information from natural images via transfer *** recent research work focuses on integrating knowledge from medical practitioners,either letting networks resemble how practitioners are trained,how they view images,or using extra *** this paper,we propose a scheme named Domain Guided-CNN(DG-CNN)to incorporate the margin information,a feature described in the consensus for radiologists to diagnose cancer in breast ultrasound(BUS)*** DG-CNN,attention maps that highlight margin areas of tumors are first generated,and then incorporated via different approaches into the *** have tested the performance of DG-CNN on our own dataset(including 1485 ultrasound images)and on a public *** results show that DG-CNN can be applied to different network structures like VGG and ResNet to improve their *** example,experimental results on our dataset show that with a certain integrating mode,the improvement of using DG-CNN over a baseline network structure ResNet 18 is 2.17%in accuracy,1.69%in sensitivity,2.64%in specificity and 2.57%in AUC(Area Under Curve).To the best of our knowledge,this is the first time that the margin information is utilized to improve the performance of deep neural networks in diagnosing breast cancer in BUS images.

关键词： medical consensus domain knowledge breast cancer diagnosis margin map deep neural network

来源：评论

学校读者我要写书评

暂无评论

Prompt-based Unifying Inference Attack on Graph Neural Networks

arXiv

引用

arXiv 2024年

作者： Wei, Yuecen Fu, Xingcheng Liu, Lingyun Sun, Qingyun Peng, Hao Hu, Chunming School of Software Beihang University Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University China

Graph neural networks (GNNs) provide important prospective insights in applications such as social behavior analysis and financial risk analysis based on their powerful learning capabilities on graph data. Nevertheless, GNNs’ predictive performance relies on the quality of task-specific node labels, so it is common practice to improve the model’s generalization ability in the downstream execution of decision-making tasks through pre-training. Graph prompting is a prudent choice but risky without taking measures to prevent data leakage. In other words, in high-risk decision scenarios, prompt learning can infer private information by accessing model parameters trained on private data (publishing model parameters in pre-training, i.e., without directly leaking the raw data, is a tacitly accepted trend). However, myriad graph inference attacks necessitate tailored module design and processing to enhance inference capabilities due to variations in supervision signals. In this paper, we propose a novel Prompt-based unifying Inference Attack framework on GNNs, named ProIA. Specifically, ProIA retains the crucial topological information of the graph during pre-training, enhancing the background knowledge of the inference attack model. It then utilizes a unified prompt and introduces additional disentanglement factors in downstream attacks to adapt to task-relevant knowledge. Finally, extensive experiments show that ProIA enhances attack capabilities and demonstrates remarkable adaptability to various inference attacks. Copyright © 2024, The Authors. All rights reserved.

关键词： Information leakage

来源：评论

学校读者我要写书评

暂无评论

Synthesis of Decoherence-Free Modes in Linear Quantum Passive Systems via Robust Pole Placement

Synthesis of Decoherence-Free Modes in Linear Quantum Passiv...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Miao, Zibo Pan, Yu Gao, Qing School of Mechanical Engineering and Automation Adaptive Robotics Harbin Institute of Technology Guangdong Key Laboratory of Intelligent Morphing Mechanisms Shenzhen518055 China The Institute of Cyber-Systems and Control College of Control Science and Engineering Zhejiang University State Key Laboratory of Industrial Control Technology Hangzhou310027 China The School of Automation Science and Electrical Engineering Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China

ISBN: (纸本)9781665410205

In this paper we extend our previous research on coherent observer-based pole placement approach to study the synthesis of robust decoherence-free (DF) modes for linear quantum passive systems, which is aimed at preservation of quantum information. In particular, DF modes can be generated by placing the poles on the imaginary axis via a coherent feedback design scheme, and these modes can further be simultaneously made robust against perturbations to the system parameters by minimizing the condition number associated with imaginary poles. We develop explicit algebraic conditions for the existence of such a coherent quantum controller, with the corresponding deign procedure provided. Examples are given to illustrate the process of tuning the DF modes towards perfect robustness via the proposed pole placement technique. © 2024 IEEE.

关键词： Poles

来源：评论

学校读者我要写书评

暂无评论

Identifying spatiotemporal traffic patterns in large-scale urban road networks using a modified nonnegative matrix factorization algorithm

引用

Journal of Traffic and Transportation Engineering(English Edition) 2020年第4期7卷 529-539页

作者： Xiaolei Ma Yi Li Peng Chen School of Transportation Science and Engineering Beihang UniversityBeijing 100191China Beiing Advanced Innovation Center for Big Data and Brain Computing Beihang UniversityBeiing 100191China

The identification and analysis of spatiotemporal traffic patterns in road networks constitute a crucial process for sophisticated traffic management and *** methods based on mathematical equations and statistical models can hardly be applicable to large-scale urban road networks,where traffic states exhibit high degrees of dynamics and ***,advances in data collection and processing have provided new opportunities to effectively understand spatiotemporal traffic patterns in large-scale road networks using data-driven ***,limited efforts have been exerted to explore the essential structure of the networks when conducting a spatiotemporal analysis of traffic *** this end,this study proposes a modified nonnegative matrix factorization algorithm that processes high-dimensional traffic data and provides an improved representation of the global traffic *** matrix factorization,cluster analysis is conducted based on the obtained low-dimensional representative matrices,which contain different traffic patterns and serve as the basis for exploring the temporal dynamics and spatial structure of network *** applicability and effectiveness of the proposed approach are examined in a road network of Beijing,*** show that the methods exhibit considerable potential for identifying and interpreting the spatiotemporal traffic patterns over the entire network and provide a systematic and efficient approach for analyzing the network-level traffic state.

关键词： Large-scale network Traffic state Spatiotemporal patterns Nonnegative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

An overview on the designs of distributed observers in LTI multi-agent systems

引用

Science China(Technological Sciences) 2021年第11期64卷 2337-2346页

作者： PEI YingQing GU HaiBo LIU KeXin LU JinHu Key Laboratory of Systems and Control Academy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing 100190China School of Mathematical Sciences University of Chinese Academy of SciencesBeijing 100049China School of Automation Science and Electrical Engineering Beijing Advanced Innovation Center for Big Data and Brain ComputingBeihang UniversityBeijing 100191China

With the rapid development of information technologies and cloud computing, sensor networks play an increasingly important role in our society. Over the past few decades, distributed observer theory has attracted unprecedented attention due to its wide potential applications in different areas. Meanwhile, various approaches and algorithms have been proposed and investigated. The design of distributed observers is one of the frontier topics of system and control research, which has the significant theoretical values and broad application prospects. This paper attempts to review the representative models and the corresponding approaches for distributed observer design in linear time-invariant(LTI) systems. Firstly, the research backgrounds and main advances of distributed observer designs are briefly reviewed. Then, recent results of distributed observer designs for discrete-time and continuous-time LTI multi-agent systems(MASs) are introduced in detail, respectively. Finally, the prospects and the future work directions of the design of distributed observers are put forward. The main purpose of this paper is to promote the emerging topic on the designs of distributed observers, with focuses on the interdisciplinary interest from technological sciences.

关键词： multi-agent system linear time-invarient system distributed observer consensus

来源：评论

学校读者我要写书评

暂无评论

Cooperative Channel Assignment for VANETs Based on Dual Reinforcement Learning

引用

Computers, Materials & Continua 2021年第2期66卷 2127-2140页

作者： Xuting Duan Yuanhao Zhao Kunxian Zheng Daxin Tian Jianshan Zhou Jian Gao Beijing Advanced Innovation Center for Big Data and Brain Computing Beijing100191China School of Transportation Science and Engineering Beihang UniversityBeijing100191China Department of Engineering and Design University of SussexBrightonBN19RHUK Research Institute of Highway Ministry of Transport Beijing100088China

Dynamic channel assignment(DCA)is significant for extending vehicular ad hoc network(VANET)capacity and mitigating ***,the un-known global state information and the lack of centralized control make channel assignment performances a challenging task in a distributed vehicular direct communication *** our preliminary field test for communication under V2X scenario,we find that the existing DCA technology cannot fully meet the communication performance requirements of *** order to improve the communication performance,we firstly demonstrate the feasibility and potential of reinforcement learning(RL)method in joint channel selection decision and access fallback adaptation design in this ***,a dual reinforcement learning(DRL)-based cooperative DCA(DRL-CDCA)mechanism is ***,DRL-CDCA jointly optimizes the decision-making behaviors of both the channel selection and back-off adaptation based on a multi-agent dual reinforcement learning ***,nodes locally share and incorporate their individual rewards after each communication to achieve regional consistency *** results show that the proposed DRL-CDCA can better reduce the one-hop packet delay,improve the packet delivery ratio on average when compared with two other existing mechanisms.

关键词： Vehicular ad hoc networks reinforcement learning dynamic channel assignment

来源：评论

学校读者我要写书评

暂无评论

Does Graph Distillation See Like Vision dataset Counterpart?

arXiv

引用

arXiv 2023年

作者： Yang, Beining Wang, Kai Sun, Qingyun Ji, Cheng Fu, Xingcheng Tang, Hao You, Yang Li, Jianxin School of Computer Science and Engineering Beihang University China Advanced Innovation Center for Big Data and Brain Computing Beihang University China National University of Singapore Singapore Carnegie Mellon University United States

Training on large-scale graphs has achieved remarkable results in graph representation learning, but its cost and storage have attracted increasing concerns. Existing graph condensation methods primarily focus on optimizing the feature matrices of condensed graphs while overlooking the impact of the structure information from the original graphs. To investigate the impact of the structure information, we conduct analysis from the spectral domain and empirically identify substantial Laplacian Energy Distribution (LED) shifts in previous works. Such shifts lead to poor performance in cross-architecture generalization and specific tasks, including anomaly detection and link prediction. In this paper, we propose a novel Structure-broadcasting Graph dataset Distillation (SGDD) scheme for broadcasting the original structure information to the generation of the synthetic one, which explicitly prevents overlooking the original structure information. Theoretically, the synthetic graphs by SGDD are expected to have smaller LED shifts than previous works, leading to superior performance in both cross-architecture settings and specific tasks. We validate the proposed SGDD across 9 datasets and achieve state-of-the-art results on all of them: for example, on the YelpChi dataset, our approach maintains 98.6% test accuracy of training on the original graph dataset with 1,000 times saving on the scale of the graph. Moreover, we empirically evaluate there exist 17.6% ∼ 31.4% reductions in LED shift crossing 9 datasets. Extensive experiments and analysis verify the effectiveness and necessity of the proposed designs. The code is available in the https://***/RingBDStack/SGDD. Copyright © 2023, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：